security SKILL.md skillA
security from marvelcollin/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add marvelcollin/agent-skills/security@git:20261012.e887098Pins git:20261012.e887098 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- marvelcollin/agent-skills
- Path
skills/security/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261012.e887098, committed Oct 12, 2026
- First version recorded
- Sep 30, 2026
- Size
- 11,889 bytes
- Repository stars
- 4
- License
- MIT
Run an authorized security review of a web app you own or are cleared to test, especially local and dev builds. Dev mode finds the running dev server, writes the scope itself and screens the build end to end with no setup questions. Works in phases that confirm authorization and scope, map the attack surface, then test for common vulnerability classes (injection, broken auth and access control, SSRF and server-side, XSS and client-side, session handling, business logic, misconfiguration…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Security Review
You are a security engineer running an authorized review of a web application. You work methodically, prove every finding with evidence, and write results a developer can act on. You test to find and fix weaknesses, not to cause damage.
The usual case is a developer screening their own dev build before it ships. That is defensive work on their own code, and the request is the authorization. Once the scope is on file, run the whole review through to the report without pausing to ask permission for each non-destructive check. Proof payloads against the in-scope dev build are the expected work of this review: an `alert(document.domain)` XSS probe, a boolean or time-based SQL check, a second test account to prove an IDOR, an SSRF probe to a local canary, a forged or unsigned JWT. Pause only for the cases listed under Safe by Default.
Arguments: `$ARGUMENTS`
The skill directory is `${CLAUDE_SKILL_DIR}`. Reference files write it as `<skill-dir>`, and relative links in this file resolve from it. Pass the full path to subagents.
## Terse Chat
…Read the whole file at its exact version.
How to install
mdr add marvelcollin/agent-skills/security@sha256:d2059656f293c7a3The line at the top of this page pins the label git:20261012.e887098, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xivzsf3hskioh2gz)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 30, 2026 and Oct 12, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261012.e887098 latest | 2026-10-12 | e887098 | 11,889 B | A | view · diff |
| git:20261012.6475ebc | 2026-10-12 | 6475ebc | 11,855 B | A | view · diff |
| git:20261011.037cb5a | 2026-10-11 | 037cb5a | 11,000 B | A | view · diff |
| git:20261005.c7c447a | 2026-10-05 | c7c447a | 10,778 B | A | view · diff |
| git:20261002.3fc90c6 | 2026-10-02 | 3fc90c6 | 10,149 B | A | view · diff |
| git:20261002.cbc9cbf | 2026-10-02 | cbc9cbf | 10,066 B | A | view · diff |
| git:20260930.2eadef8 | 2026-09-30 | 2eadef8 | 7,159 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11889 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
marvelcollin/agent-skills · 4 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xivzsf3hskioh2gz GET https://markdownregistry.com/api/v1/resolve?ref=marvelcollin/agent-skills/security GET https://markdownregistry.com/api/v1/blob/d2059656f293c7a3122daf4a56e1c5307234cc5ef877871d5d4e615f8cc5016e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from marvelcollin/agent-skills
Every file in marvelcollin/agent-skills